R-ORD GOLD-ONLY ordering-over-numeric-text
formula_1 · mini_dev_postgresql from https://bird-bench.oss-cn-beijing.aliyuncs.com/minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f, downloaded 2026-09-07), member minidev/MINIDEV/mini_dev_postgresql.json
For the driver who set the fastest lap speed, what is his nationality?
the hint the set supplies: the fastest lap speed refers to (MAX) fastestLapSpeed;
This question was audited without a prediction beside it, so there is nothing to compare the gold with. The probes below read the gold alone.
SELECT T1.nationality FROM drivers AS T1 INNER JOIN results AS T2 ON T2.driverId = T1.driverId ORDER BY T2.fastestLapSpeed DESC NULLS LAST LIMIT 1sha256:189fafa0be55b3a5c228e0520834b2ab101cf58ee69c272a21e8c920d55a59bd
from evidence-gold.json, 1 row
| nationalitytext |
|---|
| Italian |
A smell is a mechanical reason to read this gold statement again. It is a heuristic: it does not state that the statement is wrong, and a maintainer decides.
this statement orders by a text column holding only numbers, and ordering it as a number gives a different answer, so the gold may be sorting 9.5 above 10
from smells.json, 1 row
| Italian |
{
"heuristic": true,
"keys": [
{
"key": "t2.fastestlapspeed",
"column": "results.fastestlapspeed",
"declared_type": "text",
"not_applicable": null,
"census": {
"rows": 23179,
"nulls": 18185,
"empty_strings": 0,
"non_numeric": 0,
"pattern": "^-?[0-9]+(\\.[0-9]+)?$"
},
"every_value_is_numeric": true,
"cast_sql": "SELECT t1.nationality FROM drivers t1 JOIN results t2 ON t2.driverid = t1.driverid ORDER BY t2.fastestlapspeed::numeric DESC NULLS LAST LIMIT 1",
"verdict": "not_equal",
"gold_result": {
"columns": [
{
"name": "nationality",
"declared_type": "text"
}
],
"row_count": 1,
"truncated": false,
"rows_shown": 1,
"rows": [
[
{
"type": "str",
"value": "Italian"
}
]
],
"result_hash": "sha256:189fafa0be55b3a5c228e0520834b2ab101cf58ee69c272a21e8c920d55a59bd"
},
"cast_result": {
"columns": [
{
"name": "nationality",
"declared_type": "text"
}
],
"row_count": 1,
"truncated": false,
"rows_shown": 1,
"rows": [
[
{
"type": "str",
"value": "Brazilian"
}
]
],
"result_hash": "sha256:a3a555097c048e3ef0b28670b816e999135504a4fdb81a738305ee48fc26adb4"
}
}
]
}this statement cuts its result at a LIMIT that does not decide which rows come back, so a different but equally correct statement can return other rows and score zero
{
"heuristic": true,
"cut": 1,
"offset": 0,
"distinct_kept": false,
"unbounded_sql": "SELECT t1.nationality, t2.fastestlapspeed AS attestql_ordering_key_0 FROM drivers t1 JOIN results t2 ON t2.driverid = t1.driverid ORDER BY t2.fastestlapspeed DESC NULLS LAST",
"unbounded_rows": 23179,
"projected_columns": [
"nationality"
],
"ordering_key_columns": [
"attestql_ordering_key_0"
],
"ordering_keys": [
{
"key": "t2.fastestlapspeed",
"direction": "desc",
"nulls": "last",
"nulls_first_in_effect": false,
"returned_rows_null_in_this_key": 0,
"fires": false
}
],
"case": null
}rerun over the same rows in another physical order this statement gives another answer, so its result depends on how the rows are stored and not only on the data
{
"heuristic": true,
"rule": "R-ORD",
"baseline_result_hash": "sha256:189fafa0be55b3a5c228e0520834b2ab101cf58ee69c272a21e8c920d55a59bd",
"baseline_result": {
"columns": [
{
"name": "nationality",
"declared_type": "text"
}
],
"row_count": 1,
"truncated": false,
"rows_shown": 1,
"rows": [
[
{
"type": "str",
"value": "Italian"
}
]
],
"result_hash": "sha256:189fafa0be55b3a5c228e0520834b2ab101cf58ee69c272a21e8c920d55a59bd"
},
"planner_statistics": {
"drivers": {
"last_analyze": null,
"last_autoanalyze": null,
"n_mod_since_analyze": 840
},
"results": {
"last_analyze": null,
"last_autoanalyze": null,
"n_mod_since_analyze": 23179
}
},
"shuffle": {
"seed": "1",
"row_limit": 300000,
"tables": [
"drivers",
"results"
],
"tables_not_shuffled": [],
"tables_skipped_for_size": {
"laptimes": 400524,
"legalities": 427907,
"posthistory": 303155,
"trans": 1056320,
"yearmonth": 383282
},
"tables_not_reached_by_a_copy": {}
},
"shuffled_copies": {
"run": true,
"verdict": "equal",
"differs": false,
"result_hash": "sha256:189fafa0be55b3a5c228e0520834b2ab101cf58ee69c272a21e8c920d55a59bd",
"result": {
"columns": [
{
"name": "nationality",
"declared_type": "text"
}
],
"row_count": 1,
"truncated": false,
"rows_shown": 1,
"rows": [
[
{
"type": "str",
"value": "Italian"
}
]
],
"result_hash": "sha256:189fafa0be55b3a5c228e0520834b2ab101cf58ee69c272a21e8c920d55a59bd"
}
},
"plan_variant": {
"run": false,
"reason": "the plan variant was not asked for"
}
}SELECT T1.nationality FROM drivers AS T1 INNER JOIN results AS T2 ON T2.driverId = T1.driverId ORDER BY T2.fastestLapSpeed DESC NULLS LAST LIMIT 1result_hash sha256:189fafa0be55b3a5c228e0520834b2ab101cf58ee69c272a21e8c920d55a59bd recomputed from this JSON: match
record_hash sha256:304245afdda7782d244ad989ed66593c24d13e1a87e346db11b5cbccfc46fa07 recomputed from this JSON: match
from evidence-gold.json, 1 row
| nationalitytext |
|---|
| Italian |
re-run this statement read-only against PostgreSQL 16.15 (Debian 16.15-1.pgdg13+2) on aarch64-unknown-linux-gnu, compiled by gcc (Debian 14.2.0-19) 14.2.0, 64-bit | server=172.17.0.2/32:5432 | database=bird under the session settings and over the data this record's fixture digest names, and compare the two results under R-ORD